Research map / Video / Video generation
ARIG: Autoregressive Interactive Head Generation for Real-time Conversations
Ying Guo, Xi Liu, Cheng Zhen, Pengfei Yan, Xiaoming Wei
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add long-range context in the interactive behavior understanding module (ablation) | ARIG · RealTalk | RPCC: 0.140 -> 0.125 | Improved |
| add conversational state guidance (CSU) (ablation) | ARIG · RealTalk | SyncScore: 6.973 -> 7.218 | Improved |
| add visual modality of the user to IBU (ablation) | ARIG · RealTalk | RPCC: 0.155 -> 0.125 | Improved |
| use continuous diffusion-based AR modeling instead of discrete codebook indices (ablation) | ARIG · RealTalk | FID: 23.78 -> 21.64 | Improved |
| add bidirectional-integrated learning in IBU instead of linear layers (ablation) | ARIG · RealTalk | PSNR: 24.17 -> 29.67 | Improved |
| use ARIG instead of DIM | DIM · RealTalk | SyncScore: 4.192 -> 7.218 | Improved |
| apply ARIG to single-role talking head without fine-tuning versus EchoMimic | ARIG · HDTF | PSNR: 28.65 (EchoMimic) vs 28.63 | No clear effect |
| ARIG versus INFP on pose variance in listening head generation | ARIG · ViCo listening (pose) | Var: 0.18 (INFP) vs 0.17 | Hurt |
Later papers that compared with this method
1 later accepted paper reports ARIG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation (ECCV 2026 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations (CVPR 2025 · similarity 0.87)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.87)
- CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation (CVPR 2024 · similarity 0.86)
- Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs (ICLR 2025 · similarity 0.86)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.86)
- Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
